Skip to content

DeepCounterfeit MCP server

com.deepcounterfeit/deepcounterfeitdeepcounterfeit.comstreamable-httpv1.1.0Scanned

Solana pre-buy check, smart-money flow and imitation detection. Free tier; x402 pay-per-call.

16 tools: 10 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 10 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 1 finding

Sign-in required, no OAuth metadata. Remote posture

With Anlyon

10 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the DeepCounterfeit MCP server can do

The DeepCounterfeit MCP server is published by deepcounterfeit.com, a domain the MCP Registry verified. It has 16 tools. It can create or change data (10 tools: check_token, check_name, trace_wallet, token_manipulation_score and 6 more), but cannot delete data. 6 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 1.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

16 tools

Changes things 10Claude Code: ask
  • check_nameRun the impersonation detector on a token name and/or ticker symbol without needing an address.1 finding

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "check_name" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Run the impersonation detector on a token name and/or ticker symbol without needing an address. Tells you whether a coin called e.g. "SpaceX Official" ($SPACEX) or "TSLAx" would be flagged as impersonating a brand, which brand, and why. Use for pre-launch name checks, or when a user mentions a coin by name and you have no address (with an address, use check_token). Does not assess creator behaviour.

    Annotations the server declares

    • title: Check a token name/ticker before launch or purchase
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_tokenLook up a deployed token by contract/mint address and report whether it impersonates a real company, its "official" token or its tokenized stock (e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Look up a deployed token by contract/mint address and report whether it impersonates a real company, its "official" token or its tokenized stock (e.g. a fake SpaceX, Coinbase or NVDAx coin). Returns verdict (likely_impersonation | brand_mention_watch | not_in_index), matched brands, risk score 0-100 with reasons (creator bought supply at launch, same-block bundles, creator cash-out, serial launcher), creator wallet and explorer links. Use before buying, listing or promoting a token. "not_in_index" only means no brand match was recorded, not that the token is safe. Without an API key: brand match and coin only (flagged as likely impersonation), no risk score, creator wallet or forensics.

    Annotations the server declares

    • title: Check a token for brand impersonation
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • creator_reputationFor a token creator wallet (Solana or EVM address): how many tokens it launched, first/last launch (UTC), share of launches that were bundled (3+ wallets buying in the first slots)…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a token creator wallet (Solana or EVM address): how many tokens it launched, first/last launch (UTC), share of launches that were bundled (3+ wallets buying in the first slots), share where the creator sold 90%+ of its tokens within 10 minutes, share where liquidity was removed / the market collapsed within 24 h of launch, linked wallets (same wallet group, funding source) and exchange trail. Indicators from public on-chain data only, not financial advice and not findings about any person. Free: headline score 0-100, band and counts. Full breakdown with an API key, or x402 pay-per-call at $0.10 USDC: GET /v1/x402/creator/{wallet}.

    Annotations the server declares

    • title: Creator / wallet reputation (launch history indicators)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • forensics_caseEvidence pack for a flagged pump.fun token, creator wallet group or caller: detectors fired (bundled launch, creator sell-off, wash-like trading, sells after a call, caller sold in…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Evidence pack for a flagged pump.fun token, creator wallet group or caller: detectors fired (bundled launch, creator sell-off, wash-like trading, sells after a call, caller sold into own call, recurring launch-and-exit) each with confidence, plain-English on-chain reason and false-positive note; supporting tx signatures with Solscan links, UTC block times and amounts; timeline with price impact; per-wallet P&L; funding/exchange cash-out graph with label sources; SHA-256 integrity hash. Look up by case id (TK-/CL-/KOL-), token mint or wallet; empty = index of cases. On-chain facts only, no claims about intent or identity. Without a trial/paid key: preview (summary, detectors, hash, first transactions).

    Annotations the server declares

    • title: Forensic case file (evidence pack) for a token, creator group or caller
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_trial_keyCreate a free 14-day trial API key for your user instantly (no card): real-time data, full evidence and no daily cap instead of the keyless Free tier (24 h delayed, limited free ca…No findings

    Why it is in this group

    • The name "get_trial_key" says "get": a word for reading.
    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create a free 14-day trial API key for your user instantly (no card): real-time data, full evidence and no daily cap instead of the keyless Free tier (24 h delayed, limited free calls per day). ONLY call this with your user's explicit consent, using their own email address. The key is returned once: give it to your user and add it to this MCP connection as the X-API-Key header (or ?key= in the server URL). This tool never counts against the free daily limit.

    Annotations the server declares

    • title: Get a free 14-day API key (instant, no card)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • kol_scorecardFor a public pump.fun caller (wallet or public handle), how often its wallet bought before posting a call, median lead time, how often it sold within 1 h of the call, how often the…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a public pump.fun caller (wallet or public handle), how often its wallet bought before posting a call, median lead time, how often it sold within 1 h of the call, how often the token fell 50%+ within 1 h, calls on serial-launcher tokens, and creator-to-caller transfers found in traced creator wallets. Public handles and wallets only. Without a trial/paid key: headline numbers only.

    Annotations the server declares

    • title: Caller/KOL scorecard (pump.fun callouts vs on-chain trades)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • prebuy_checkOne fast call before buying a token (Solana mint, mainly pump.fun): verdict clear / caution / avoid / unknown, risk_score 0-100 and reasons[] (code + one line).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    One fast call before buying a token (Solana mint, mainly pump.fun): verdict clear / caution / avoid / unknown, risk_score 0-100 and reasons[] (code + one line). Combines brand imitation and older, bigger tokens with the same ticker; creator wallet reputation (score, band, confidence); bundled launch and early-holder concentration; age, trades in 24 h, liquidity and graduation. Mints not in our data return verdict unknown, never an estimate. Informational only, not financial advice, no guarantee. Free/keyless: verdict, score and reason codes; full report with any API key, or x402 pay-per-call at $0.01 USDC: GET /v1/x402/prebuy/{mint}.

    Annotations the server declares

    • title: Pre-buy check for a token (risk signals before you buy)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • smartmoney_flowFor a pump.fun token mint: how many proven wallets (statistically positive past results over the last 30 days, net of estimated fees; creators, launch-block buyers, wash-like and c…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a pump.fun token mint: how many proven wallets (statistically positive past results over the last 30 days, net of estimated fees; creators, launch-block buyers, wash-like and clustered wallets removed) bought or sold it in the last 15 min / 1 h / 24 h, their share of active wallets, net SOL flow, first proven entry time (UTC), whether they are exiting, top proven wallets with an anonymous score band, coverage and confidence. Covers pump.fun bonding-curve (pre-graduation) trades only; never estimated. Informational data only, not financial advice; past wallet performance does not predict results. Free/keyless: headline; full report with any API key, or x402 pay-per-call at $0.01 USDC: GET /v1/x402/smartmoney/{mint}.

    Annotations the server declares

    • title: Smart-money flow for a pump.fun token (what proven wallets are doing)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • token_manipulation_scoreScore 0-100 of on-chain patterns consistent with market manipulation for a pump.fun token (last 72 h): bundled launch, creator sell-off, coordinated early-wallet dump, wash-like ro…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Score 0-100 of on-chain patterns consistent with market manipulation for a pump.fun token (last 72 h): bundled launch, creator sell-off, coordinated early-wallet dump, wash-like round-trip volume, serial-launcher group, collapse with early wallets in profit; plus the creator's exchange cash-out trail when traced. Without a trial/paid key: score and patterns only.

    Annotations the server declares

    • title: Pump-and-dump / manipulation score for a pump.fun token
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • trace_walletFor a Solana wallet (typically a token creator), return where its SOL/USDC went: transfers followed up to 3 hops to exchange hot wallets (Binance, OKX, Coinbase, Bybit, ...No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For a Solana wallet (typically a token creator), return where its SOL/USDC went: transfers followed up to 3 hops to exchange hot wallets (Binance, OKX, Coinbase, Bybit, ... from a public label set), likely exchange deposit addresses, its funding source, and its wallet group (linked creator wallets, serial-launch statistics). Covers wallets in the current forensics snapshot (creators of flagged impersonation coins, serial launchers, creators of KOL-called tokens). Patterns only, not findings about any person. Without a trial/paid key: summary preview.

    Annotations the server declares

    • title: Trace a Solana wallet to exchanges (cash-out trail)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 6Show 6 read-only tools
  • fetchFetch the full check_token result for a result id returned by search (format "<chain>:<address>"): verdict, matched brands, match type and explorer links; with an API key also risk…No findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.
    Description, as the server wrote it
    Fetch the full check_token result for a result id returned by search (format "<chain>:<address>"): verdict, matched brands, match type and explorer links; with an API key also risk score, reasons and creator facts. Use after search; for a known address call check_token directly.

    Annotations the server declares

    • title: Fetch (ChatGPT connector)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_brand_reportSummarise impersonation activity against one brand over a window: number of fake coins, traded volume, breakdown by chain/match type/severity, repeat creator wallets, how many crea…No findings

    Why it is in this group

    • The name "get_brand_report" says "get": a word for reading.
    Description, as the server wrote it
    Summarise impersonation activity against one brand over a window: number of fake coins, traded volume, breakdown by chain/match type/severity, repeat creator wallets, how many creators bought 50%+ of supply, and the top cases with evidence. Pro/Wholesale keys also get the takedown-ready PDF link.

    Annotations the server declares

    • title: Brand impersonation report
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_statsAggregate numbers for a window: alerts, high-severity count, brands hit, by chain, by match type, top brands, data-source health and coverage.No findings

    Why it is in this group

    • The name "get_stats" says "get": a word for reading.
    Description, as the server wrote it
    Aggregate numbers for a window: alerts, high-severity count, brands hit, by chain, by match type, top brands, data-source health and coverage. Use for overviews, trend questions and to check data freshness.

    Annotations the server declares

    • title: Impersonation statistics
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_brandsList the brands on the watchlist (companies, tokenized stocks, crypto projects, private companies) with ids, tickers and all-time alert counts, most-targeted first.No findings

    Why it is in this group

    • The name "list_brands" says "list": a word for reading.
    Description, as the server wrote it
    List the brands on the watchlist (companies, tokenized stocks, crypto projects, private companies) with ids, tickers and all-time alert counts, most-targeted first. Use to find a brand id or check whether a brand is covered.

    Annotations the server declares

    • title: List watched brands
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_alertsList recent impersonation coins, newest first, filtered by brand, chain, time and severity.No findings

    Why it is in this group

    • The name "search_alerts" says "search": a word for reading.
    Description, as the server wrote it
    List recent impersonation coins, newest first, filtered by brand, chain, time and severity. Use to answer "are there fake <brand> tokens?", to monitor a brand, or to collect cases for a takedown. Free tier returns alerts older than 24 h only (max 20).

    Annotations the server declares

    • title: Search impersonation alerts
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 18:37 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
525
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: initialize answered HTTP 525.

Posture changes

  1. Nov 13, 2026
    • HTTP status of an anonymous initialize: 502 to 525
  2. Nov 6, 2026
    • HTTP status of an anonymous initialize: 200 to 502
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 10 to 0
    • Protocol version: 2025-06-18 to none
  3. Oct 29, 2026
    • Tools that change things, listed without credentials: 2 to 10

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "check_name" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "run": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 502 -> 525.View diff
    • HTTP status of an anonymous initialize: 502 to 525
  2. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 502; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 10 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 502
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 10 to 0
    • Protocol version: 2025-06-18 to none
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 2 -> 10.View diff
    • Tools that change things, listed without credentials: 2 to 10
  4. Tools8 added.+8 addedView diff

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http deepcounterfeit https://deepcounterfeit.com/mcp
claude mcp add --transport http deepcounterfeit https://deepcounterfeit.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__deepcounterfeit__search_alerts",
      "mcp__deepcounterfeit__get_brand_report",
      "mcp__deepcounterfeit__list_brands",
      "mcp__deepcounterfeit__get_stats",
      "mcp__deepcounterfeit__search",
      "mcp__deepcounterfeit__fetch"
    ],
    "ask": [
      "mcp__deepcounterfeit__check_token",
      "mcp__deepcounterfeit__check_name",
      "mcp__deepcounterfeit__trace_wallet",
      "mcp__deepcounterfeit__token_manipulation_score",
      "mcp__deepcounterfeit__kol_scorecard",
      "mcp__deepcounterfeit__forensics_case",
      "mcp__deepcounterfeit__creator_reputation",
      "mcp__deepcounterfeit__prebuy_check",
      "mcp__deepcounterfeit__smartmoney_flow",
      "mcp__deepcounterfeit__get_trial_key"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as deepcounterfeit. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.deepcounterfeit/deepcounterfeit/verify?hash=65420f7b2139bacdcc756e0cab71f1935039a67a85e096dbde5bd6d68a6596aa" | jq -e '.changed == false'

Pinned hash 65420f7b2139, from Nov 9, 2026, 14:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.deepcounterfeit/deepcounterfeit/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.deepcounterfeit/deepcounterfeit
[![Anlyon Radar](https://radar.anlyon.com/badge/com.deepcounterfeit/deepcounterfeit.svg)](https://radar.anlyon.com/servers/com.deepcounterfeit/deepcounterfeit)

Source: MCP Registry. Synced Oct 27, 2026, 08:17 UTC.

DeepCounterfeit MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the DeepCounterfeit MCP server safe?

No scan can promise that. What its definitions show: 16 tools, 10 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the DeepCounterfeit MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the DeepCounterfeit MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the DeepCounterfeit MCP server have?

16 tools: 10 write, 6 read. check_token, check_name, trace_wallet, token_manipulation_score, kol_scorecard, forensics_case, creator_reputation, prebuy_check and 8 more.

Does the DeepCounterfeit MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the DeepCounterfeit MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the DeepCounterfeit MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 27, 2026. Every change is on this page and in its Atom feed.